Answers are grounded in this paper and cite their sources.
Framework integrates XR technologies to enhance training in shipyards, highlighting risk-based decision support.
This paper presents a framework for accelerating shipyard modernization by integrating Extended and Virtual Reality (XR/VR) technologies into drydock training. Leveraging SBIR/STTR technologies and powered by Agentic AI, the proposed system translates frontline operational issues into Navy Quad Charts, maps them to relevant innovations, and prioritizes solutions using a risk-based dashboard. Key AR/VR applications include maintenance, docking/undocking, and emergency response training. The framework enhances communication, reduces risk, and supports informed technology adoption decisions. This effort aligns with global technology transfer themes by modernizing shipyard processes and improving workforce readiness through structured digital tools and immersive training strategies. INTRODUCTION The modernization of shipyard operations, particularly in high-risk environments such as drydocks, is critical to ensuring the safety, efficiency, and long-term sustainability of naval and commercial maritime activities. Despite the rapid advancement of Industry 4.0 and 5.0 technologies—ranging from robotics to immersive Extended Reality (XR) and Virtual Reality (VR) systems—widespread adoption in public and private shipyards has been slowed by a lack of streamlined technology transfer mechanisms and workforce readiness. Traditional training and communication frameworks have not kept pace with emerging technologies, resulting in gaps between operational needs on the shipyard "deck plate" and the scientific or engineering language in which advanced technologies are typically framed. We present a structured, AI-enabled framework for identifying, translating, and integrating mature Navy SBIR/STTR-funded XR/VR technologies into shipyard drydock operations. By specifically focusing Agentic AI models to support decision-making as "technical translators", we aim to bridge communication between shipyard workers, technology databases, and acquisition stakeholders. The framework enables real-time conversion of workforce-identified problems into standardized Navy Quad Charts that communicate the initial problem, provide examples of existing SBIR/STTR solutions (where applicable), illuminates the contextual relevance of the solutions and identifies gaps and provides an executive summary. Retrieval-Augmented Generation (RAG) models (Lewis et al., 2020) paired with Large Language Models (LLMs) (Devlin et al., 2019; Radford et al., 2018) based on the transformer architecture (Vaswani et al., 2017) are utilized to identify and evaluate existing solutions within the context of the identified problem and to evaluate their suitability via a risk-based decision dashboard. This process allows for a consistent exploration of the application of these technologies for drydock-related training scenarios, including ship docking/undocking, preventive maintenance, and emergency response.
No takes yet. Share an insight, caveat, or question.
Lynch et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: